Human Spine Motion Capture using Perforated Kinesiology Tape

TL;DR

This paper introduces a marker-based multi-view spine tracking system using perforated kinesiology tape and deep learning for accurate, fast, and robust motion capture suitable for sports activities.

Contribution

The work presents a novel spine motion capture method leveraging prior tape dot arrangement, combining Mask R-CNN detection with 3D reasoning for improved accuracy and speed.

Findings

High precision and marker density achieved

Robustness against occlusions demonstrated

Capable of capturing fast movements

Abstract

In this work, we present a marker-based multi-view spine tracking method that is specifically adjusted to the requirements for movements in sports. A maximal focus is on the accurate detection of markers and fast usage of the system. For this task, we take advantage of the prior knowledge of the arrangement of dots in perforated kinesiology tape. We detect the tape and its dots using a Mask R-CNN and a blob detector. Here, we can focus on detection only while skipping any image-based feature encoding or matching. We conduct a reasoning in 3D by a linear program and Markov random fields, in which the structure of the kinesiology tape is modeled and the shape of the spine is optimized. In comparison to state-of-the-art systems, we demonstrate that our system achieves high precision and marker density, is robust against occlusions, and capable of capturing fast movements.